OpenBMB
Tags for speech
Hey! Does the model supports <Laughter>, <Breath>, <Cry> etc tokens?
If not, how to add them in the model?
Hey! Does the model supports , , etc tokens?
If not, how to add them in the model?
I can't see the tags you mentioned, but currently the model doesn't support any tags.
My bad! I meant laugh, breathe, cry like tags. If the model doesn't support them, how can we add them to it? Or maybe add instructions to model like: "Speak in an angry tone."
My bad! I meant laugh, breathe, cry like tags. If the model doesn't support them, how can we add them to it? Or maybe add instructions to model like: "Speak in an angry tone."
The current model does not support these tags, but I think with some fine-tuning it might be able to. We are also working on providing support for these tags. If we succeed, we will release it in future versions.
Can you share how can we add instructions as well? I tried to append it before the prompt text, but it started bleeding it into the generated audio.